Free Webinar: Development of Automated Chemometric Platform for Accelerated Raman-based Model Optimization in Biologics

BioPharma-Asia webinar registrationBrian Rohrback, president of Infometrix, will join Oliver Steinhof, PAT Scientist at Biogen and Nicolas Langenegger, Senior Associate Scientist at Biogen for this free webinar on September 20, 2021 at 10:00am EST.

Register at: biopharma-asia.com

The increasing use of multivariate models both as part of the control strategy in commercial (bio)pharmaceutical production as well as for process monitoring calls for an efficient strategy for model development and model life cycle management. The traditional approach to develop multivariate models based on spectroscopy involves manual data management such as selection and transfer of spectroscopic data, import into modeling software and selection/exclusion of data. That is followed by addition of reference data, alignment of time stamps and import into the modeling software. 90% of the time required to construct a multivariate model is spent on data preparation. It was decided to develop a solution to automate these steps to prepare (stage) the data required for model development, reducing the time required to prepare a typical set of batch data to about five minutes. A second tool was developed to automatically optimize data pretreatment parameters and spectral range for PLS models. Both tools allow our scientists to invest their time into more value-added activities.

ISA Virtual Conference: Rethinking Calibration for Process Spectrometers

ISA 2021 Virtual ConferenceJoin Brian Rohrback at the 2021 ISA Analysis Division Virtual Conference

March 23, 2021 at 12:00 ET

Register and be ready to take part in these in-depth discussions at www.isa.org/ad

 

Rethinking Calibration for Process Spectrometers

The talk focuses on a generic, machine-learning approach that addressed the primary bottlenecks of mustering data, automating analyzer calibration, and tracking data and model performance over time. The gain in efficiency has been considerable, and the fact that the approach does not disturb any of the legacy (i.e., no changes or alterations to any analyzer or software in place) made deployment simple. The result is a standardized procedure for doing calibrations that adheres to best practices, archives all data and models with easy access in mind, and delivers models in any format.

ISA Webinar – Practical AI: In Search of Dynamic, Autonomous Process Analytics

ISA 2021 webinar postingJoin Brian Rohrback, President of Infometrix on Feb. 25th at 1:00pm ET.

Free Webinar: Process Control & Instrumentation Series

 

 

Practical AI: In Search of Dynamic, Autonomous Process Analytics

The application of the concepts behind artificial intelligence and machine learning mandates a systematic approach to extracting information from multiple, byte-dense data sources. Effective extraction of this information leads to improvements in decision making at all levels of the chemical, petrochemical, and petroleum industries. To accomplish anything in the AI space, we need to combine traditional approaches in statistics, database organization, pattern recognition, and chemometrics with some newer concepts tied to better understanding of data mining, neurocomputing, and machine learning. This is an introduction to a practical approach to deploying AI and how a multi-company, multi-industry, hydrocarbon processing consortium, established eight years ago to re-evaluate how the calibration process for sensors and analyzers could be managed more efficiently. The focus spans optical spectrometers, chromatographs, and process sensors, independently and in combination, with a shift from current practices to approaches that take advantage of the computational power at our fingertips.

Dr. Rohrback’s expertise covers the integration of multivariate data processing for process analyzers and laboratory instruments catering to routine quality analysis. Prior to his current position, he worked for Cities Services Oil Company, now Occidental Petroleum, with industry positions including research scientist managing the chromatography group, an exploration geologist, and manager of planning/budget for EAME. He holds a B.S. in chemistry, a Ph.D. in organic geochemistry, and an MBA. His 50-year span of published works include topics in petroleum exploration, chemical plant optimization, clinical and pharmaceutical diagnostics, informatics, pattern recognition and multivariate analysis.

2020 AIChE Spring Meeting and 16th Global Congress on Process Safety

 2020 AIChE Spring Meeting and 16th Global Congress on Process Safety
Aug 19, 2020
Virtual Meeting

See abstract below for presentation at the 2020 AIChE Spring Meeting. Join us or contact us for more information.

 

Harnessing Big Data Approaches and AI in the Chemical Processing Industry
Brian Rohrback – Infometrix

The term Big Data implies a systematic approach to extracting information from multiple, byte-dense data sources. Effective extraction of this information leads to improvements in decision making at all levels of the chemical, petrochemical, and petroleum industries. To accomplish anything in the Big Data space, we need to combine traditional approaches in statistics, database organization, pattern recognition, and chemometrics with some newer concepts tied to better understanding of data mining, neuro-computing, and machine learning. In order for industry to achieve the goals that this form of AI promises, we need to approach the issues with more than just words.

This is a summary of a multi-company, multi-industry, hydrocarbon processing consortium, established seven years ago to re-evaluate how the calibration process for sensors and analyzers could be managed more efficiently. The focus spans optical spectrometers, chromatographs, and process sensors, independently and in combination. The idea is to enable a shift from current practices to approaches that take advantage of the computational power at our fingertips. It was critical to prioritize solutions that are non-disruptive, utilize legacy systems, and lessen the workload rather than layer on additional requirements. The result is a choice of tools available to consume the data and generate actionable, process-specific information are in hand. The analyzers in place, optical spectrometers in particular, represent the low-hanging fruit.

ISA 2020 – Rethinking Calibration for Process Spectrometers II

The Long Beach Convention Center
Long Beach, CA
1:30pm, April 27th

 

Brian Rohrback
Infometrix, Inc.
Will Warkentin
Chevron Richmond Refinery

 

KEYWORDS
Best Practices, Calibration, Cloud Computing, Database, Gasoline Blending, Optical Spectroscopy, PLS, Process Control

ABSTRACT
Optical spectroscopy is a favored technology to measure chemistry and is ubiquitous in the hydrocarbon processing industry. In a previous paper, we focused on a generic, machine-learning approach that addressed the primary bottlenecks of mustering data, automating analyzer calibration, and tracking data and model performance over time. The gain in efficiency has been considerable, and the fact that the approach does not disturb any of the legacy (i.e., no changes or alterations to any analyzer or software in place) made deployment simple.

We also standardized a procedure for doing calibrations that, adheres to best practices, archives all data and models, provides ease of access, and delivers the models in any format. What remains is to assess the speed of processing and the quality of the models. To that end a series of calibration experts were tasked with model optimization, restricting the work to selecting the proper samples to include in the computation and setting the number of factors in PLS.  The amount of time and the quality of the models were then compared.  The automated system performed the work in minutes rather than hours and the quality of the predictions at least matched the best experts and performed significantly better than the average expert.  The conclusion is that there is a large amount of recoverable giveaway that can be avoided through automation of this process and the consistency it brings to the PLS model construction.

INTRODUCTION
There is a lot of mundane work tied to the assembly of spectra and laboratory reference values to enable quality calibration work.  There is also insufficient guidance when it comes to the model construction task.  How much time should be spent on this task?  How to best assess whether a spectrum-reference pair is an outlier or not? How many cycles of regression-sample elimination make sense? Where do we switch over from improving the model by adding PLS factors to overfitting and incorporating destabilizing noise?

For more information or the full paper, contact us.